import numpy as np
import pandas as pd
from LFSpy import LocalFeatureSelection
from timeit import default_timer as timer

#number of random numbers to generate
datalen = 500 

#number of features the dataset will have
datavars = 5

#set random number seed
rng_seed = 125
rng = np.random.default_rng(rng_seed)

#generate the numbers
data = rng.uniform(-1.0,1.0,size=datalen)

#shape our dataset
data = data.reshape([datalen//datavars,datavars])

#set up container for class labels
class_labels = np.zeros(shape=data.shape[0],dtype=np.uint8)

#set the class labels
for i in range(data.shape[0]):
    class_labels[i] = 1 if (data[i,1] > 0.0 and data[i,2] > 0.0) or (data[i,1] < 0.0 and data[i,2] < 0.0) else 0

#partition our training data
xtrain = data
ytrain = class_labels

#initialize the LFS object
lfs = LocalFeatureSelection(rr_seed=rng_seed,alpha=8,tau=2,n_beta=20,nrrp=2000)

#start timer
start = timer()

#train the model
lfs.fit(xtrain,ytrain)

#output training duration
print("Training done in ", timer()-start , " seconds. ")

#get the inclusion matrix
fstar = lfs.fstar

#add up all ones for each row of the inclusion matrix
ibins = fstar.sum(axis=1)

#calculate the percent of times a candidate was selected
original_crits = 100.0 * ibins.astype(np.float64)/np.float64(ytrain.shape[0])

#output the results
print("------------------------------> Percent of times selected <------------------------------" )
for i in range(original_crits.shape[0]):
   print( f" Variable at column {i}, selected {original_crits[i]} %")